E5-base

新闻（2023年5月）：请切换到 e5-base-v2 ，该模型性能更好，使用方法相同。

Text Embeddings by Weakly-Supervised Contrastive Pre-training . Liang Wang，Nan Yang，Xiaolong Huang，Binxing Jiao，Linjun Yang，Daxin Jiang，Rangan Majumder，Furu Wei，arXiv 2022

该模型有12层，嵌入大小为768。

使用方法

以下是一个例子，用于对MS-MARCO段落排序数据集中的查询和段落进行编码。

import torch.nn.functional as F

from torch import Tensor
from transformers import AutoTokenizer, AutoModel


def average_pool(last_hidden_states: Tensor,
                 attention_mask: Tensor) -> Tensor:
    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]


# Each input text should start with "query: " or "passage: ".
# For tasks other than retrieval, you can simply use the "query: " prefix.
input_texts = ['query: how much protein should a female eat',
               'query: summit define',
               "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
               "passage: Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."]

tokenizer = AutoTokenizer.from_pretrained('intfloat/e5-base')
model = AutoModel.from_pretrained('intfloat/e5-base')

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())

训练细节

请参阅我们在 https://arxiv.org/pdf/2212.03533.pdf 的论文。

基准评估

查看 unilm/e5 以重现在 BEIR 和 MTEB benchmark 上的评估结果。

对Sentence Transformers的支持

以下是使用sentence_transformers的示例。

from sentence_transformers import SentenceTransformer
model = SentenceTransformer('intfloat/e5-base')
input_texts = [
    'query: how much protein should a female eat',
    'query: summit define',
    "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
    "passage: Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."
]
embeddings = model.encode(input_texts, normalize_embeddings=True)

包要求

pip install sentence_transformers〜=2.2.2

贡献者： michaelfeil

常见问题解答

1.是否需要向输入文本添加前缀“查询：”和“段落：”？

是的，这是模型训练的方式，否则性能会下降。

以下是一些经验规则：

• 对于非对称任务（如开放式QA中的段落检索，临时信息检索），相应使用“查询：”和“段落：”。

• 对于对称任务（如语义相似性，释义检索），使用“查询：”前缀。

• 如果要将嵌入用作特征（如线性探测分类，聚类），请使用“查询：”前缀。

2.为什么我重新运行的结果与模型卡中报告的结果略有不同？

transformers和pytorch的不同版本可能会导致可忽略但非零的性能差异。

引用

如果您发现我们的论文或模型对您有帮助，请考虑按以下方式引用：

@article{wang2022text,
  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2212.03533},
  year={2022}
}

限制

此模型仅适用于英文文本。长文本将被截断为最多512个标记。